Chen Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chen Zhang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Huazhong Shu
School of Computer Science and Engineering, Southeast University, Nanjing, China
3 shared publications - Guanyu Yang
Southeast University
2 shared publications A. Simon
1 shared publicationAnaïs Barateau
Univ Rennes
1 shared publication- Antoine Simon
LTSI, Universite de Rennes 1, Bât. 22, Campus de Beaulieu, Rennes, 35065, FRANCE
1 shared publication - Bastien Rigaud
Univ Rennes, CLCC Eugène Marquis, INSERM, LTSI – UMR 1099 Rennes France
1 shared publication
Latest Publications
- 26 April 2023
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 68 (9) , 095020
CMF-Net: craniomaxillofacial landmark localization on CBCT images using geometric constraint and transformer
Accurate and robust anatomical landmark localization is a mandatory and crucial step in deformation diagnosis and treatment planning for patients with craniomaxillofacial (CMF) malformations. In this paper, we propose a trainable end-to-end cephalometric landmark localization framework on Cone-beam computed tomography (CBCT) scans, referred to as CMF-Net, which combines the appearance with transformers, geometric constraint, and adaptive wing (AWing) loss. More precisely: (1) we decompose the localization task into two branches: the appearance branch integrates transformers for identifying the exact positions of candidates, while the geometric constraint branch at low resolution allows the implicit spatial relationships to be effectively learned on the reduced training data. (2) We use the AWing loss to leverage the difference between the pixel values of the target heatmaps and the automatic prediction heatmaps. We verify our CMF-Net by identifying the 24 most relevant clinical landmarks on 150 dental CBCT scans with complicated scenarios collected from real-world clinics. Comprehensive experiments show that it performs better than the state-of-the-art deep learning methods, with an average localization error of 1.108 mm (the clinically acceptable precision range being 1.5 mm) and a correct landmark detection rate equal to 79.28%. Our CMF-Net is time-efficient and able to locate skull landmarks with high accuracy and significant robustness. This approach could be applied in 3D cephalometric measurement, analysis, and surgical planning.
- 26 April 2023
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 68 (9) , 095020
CMF-Net: craniomaxillofacial landmark localization on CBCT images using geometric constraint and transformer
Accurate and robust anatomical landmark localization is a mandatory and crucial step in deformation diagnosis and treatment planning for patients with craniomaxillofacial (CMF) malformations. In this paper, we propose a trainable end-to-end cephalometric landmark localization framework on Cone-beam computed tomography (CBCT) scans, referred to as CMF-Net, which combines the appearance with transformers, geometric constraint, and adaptive wing (AWing) loss. More precisely: (1) we decompose the localization task into two branches: the appearance branch integrates transformers for identifying the exact positions of candidates, while the geometric constraint branch at low resolution allows the implicit spatial relationships to be effectively learned on the reduced training data. (2) We use the AWing loss to leverage the difference between the pixel values of the target heatmaps and the automatic prediction heatmaps. We verify our CMF-Net by identifying the 24 most relevant clinical landmarks on 150 dental CBCT scans with complicated scenarios collected from real-world clinics. Comprehensive experiments show that it performs better than the state-of-the-art deep learning methods, with an average localization error of 1.108 mm (the clinically acceptable precision range being 1.5 mm) and a correct landmark detection rate equal to 79.28%. Our CMF-Net is time-efficient and able to locate skull landmarks with high accuracy and significant robustness. This approach could be applied in 3D cephalometric measurement, analysis, and surgical planning.
- 15 December 2022
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 67 (24) , 245020
Automatic segmentation for plan-of-the-day selection in CBCT-guided adaptive radiation therapy of cervical cancer
Objective. Plan-of-the-day (PoD) adaptive radiation therapy (ART) is based on a library of treatment plans, among which, at each treatment fraction, the PoD is selected using daily images. However, this strategy is limited by PoD selection uncertainties. This work aimed to propose and evaluate a workflow to automatically and quantitatively identify the PoD for cervix cancer ART based on daily CBCT images. Approach. The quantification was based on the segmentation of the main structures of interest in the CBCT images (clinical target volume [CTV], rectum, bladder, and bowel bag) using a deep learning model. Then, the PoD was selected from the treatment plan library according to the geometrical coverage of the CTV. For the evaluation, the resulting PoD was compared to the one obtained considering reference CBCT delineations. Main results. In experiments on a database of 23 patients with 272 CBCT images, the proposed method obtained an agreement between the reference PoD and the automatically identified PoD for 91.5% of treatment fractions (99.6% when considering a 5% margin on CTV coverage). Significance. The proposed automatic workflow automatically selected PoD for ART using deep-learning methods. The results showed the ability of the proposed process to identify the optimal PoD in a treatment plan library.
- 15 December 2022
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 67 (24) , 245020
Automatic segmentation for plan-of-the-day selection in CBCT-guided adaptive radiation therapy of cervical cancer
Objective. Plan-of-the-day (PoD) adaptive radiation therapy (ART) is based on a library of treatment plans, among which, at each treatment fraction, the PoD is selected using daily images. However, this strategy is limited by PoD selection uncertainties. This work aimed to propose and evaluate a workflow to automatically and quantitatively identify the PoD for cervix cancer ART based on daily CBCT images. Approach. The quantification was based on the segmentation of the main structures of interest in the CBCT images (clinical target volume [CTV], rectum, bladder, and bowel bag) using a deep learning model. Then, the PoD was selected from the treatment plan library according to the geometrical coverage of the CTV. For the evaluation, the resulting PoD was compared to the one obtained considering reference CBCT delineations. Main results. In experiments on a database of 23 patients with 272 CBCT images, the proposed method obtained an agreement between the reference PoD and the automatically identified PoD for 91.5% of treatment fractions (99.6% when considering a 5% margin on CTV coverage). Significance. The proposed automatic workflow automatically selected PoD for ART using deep-learning methods. The results showed the ability of the proposed process to identify the optimal PoD in a treatment plan library.